US9691000B1ActiveUtility

Orientation-assisted object recognition

81
Assignee: AMAZON TECH INCPriority: Jun 15, 2012Filed: Mar 23, 2015Granted: Jun 27, 2017
Est. expiryJun 15, 2032(~5.9 yrs left)· nominal 20-yr term from priority
G06V 30/242H04N 23/64H04N 23/635H04N 23/80G06K 9/6202G06K 9/4604G06T 7/004G06T 7/70
81
PatentIndex Score
4
Cited by
21
References
20
Claims

Abstract

A user attempting to obtain information about an object can capture image information including a view of that object, and the image information can be used with a matching or identification process to provide information about that type of object to the user. Information about the orientation of the camera and/or device used to capture the image can be provided in order to limit an initial search space for the matching or identification process. In some embodiments, images can be selected for matching based at least in part upon having a view matching the orientation of the camera or device. In other embodiments, images of objects corresponding to the orientation can be selected. Such a process can increase the average speed and efficiency in locating matching images. If a match cannot be found in the initial space, images of other views and categories can be analyzed as well.

Claims

exact text as granted — not AI-modified
What is claimed is: 
     
       1. A computer-implemented method, comprising:
 receiving, from a computing device, image data, the image data representing an object at a first time; 
 receiving contextual data corresponding to the object; 
 determining, based at least on the contextual data, an orientation of the computing device relative to the object at approximately the first time; 
 determining a first viewing angle of the object; 
 providing a notification to change the orientation of the computing device to correspond with the first viewing angle of the object; 
 selecting, from a set of reference images of a plurality of objects, a subset of reference images, the subset of reference images having corresponding viewing angles and corresponding reference image data; 
 comparing the image data to the reference image data; 
 identifying matching image data, from the reference image data, the matching image data representing an item matching the object; and 
 providing information about the item. 
 
     
     
       2. The computer-implemented method of  claim 1 , further comprising:
 providing an interface to allow a user of the computing device to manually identify the object. 
 
     
     
       3. The computer-implemented method of  claim 2 , wherein the interface allows the user to manually identify the object by at least one of pointing to a visual representation of the object on the interface or drawing a boundary around the visual representation of the object on the interface. 
     
     
       4. The computer-implemented method of  claim 1 , wherein the contextual data corresponds to at least one of a location of the computing device or a distance of the computing device from the object. 
     
     
       5. The computer-implemented method of  claim 4 , wherein the location of the computing device corresponds to at least one of a GPS location, a street address, or a business establishment associated with a physical location of the computing device. 
     
     
       6. The computer-implemented method of  claim 4 , further comprising:
 determining a scale of the object based at least on the distance of the computing device from the object. 
 
     
     
       7. The computer-implemented method of  claim 4 , wherein determining the first viewing angle of the object comprises:
 determining an orientation of a product proximate the location of the computing device; and 
 determining a viewing angle that best captures the product in the determined orientation. 
 
     
     
       8. The computer-implemented method of  claim 1 , further comprising:
 providing an option to purchase the item. 
 
     
     
       9. A computing device, comprising:
 a processor; and 
 a memory device including instructions that, when executed by the processor, cause the computing device to:
 receive image data, the image data representing an object at a first time; 
 receive contextual data corresponding to the object; 
 determine, based at least on the contextual data, an orientation of the computing device relative to the object at approximately the first time; 
 determine a first viewing angle of the object; 
 provide a notification to change the orientation of the computing device to correspond with the first viewing angle of the object; 
 select, from a set of reference images of a plurality of objects, a subset of reference images, the subset of reference images having corresponding viewing angles and corresponding reference image data; 
 compare the image data to the reference image data; 
 identify matching image data, from the reference image data, that matches the image data, the matching image data representing an item matching the object; and 
 provide information about the item. 
 
 
     
     
       10. The computing device of  claim 9 , wherein the instructions further cause the computing device to:
 provide an interface to allow a user of the computing device to manually identify the object. 
 
     
     
       11. The computing device of  claim 9 , wherein the contextual data corresponds to at least one of a location of the computing device or a distance of the computing device from the object. 
     
     
       12. The computing device of  claim 11 , wherein the location of the computing device corresponds to at least one of a GPS location, a street address, or a business establishment associated with a physical location of the computing device. 
     
     
       13. The computing device of  claim 11 , wherein determining the first viewing angle of the object comprises:
 determining an orientation of a product proximate the location of the computing device; and 
 determining a viewing angle that best captures the product in the determined orientation. 
 
     
     
       14. A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to:
 receive image data, from a computing device, the image data representing an object at a first time; 
 receive contextual data corresponding to the object; 
 determine, based at least on the contextual data, an orientation of the computing device relative to the object at approximately the first time; 
 determine a first viewing angle of the object; 
 provide a notification to change the orientation of the computing device to correspond with the first viewing angle of the object; 
 select, from a set of reference images of a plurality of objects, a subset of reference images, the subset of reference images having corresponding viewing angles and corresponding reference image data; 
 compare the image data to the reference image data; 
 identify matching image data, from the reference image data, that matches the image data, the matching image data representing an item matching the object; and 
 provide information about the item. 
 
     
     
       15. The non-transitory computer-readable storage medium of  claim 14 , wherein the instructions further cause the computing system to:
 provide an interface to allow a user of the computing system to manually identify the object by at least one of pointing to a visual representation of the object on the interface or drawing a boundary around the visual representation of the object on the interface. 
 
     
     
       16. The non-transitory computer-readable storage medium of  claim 14 , wherein the contextual data corresponds to at least one of a location of the computing device or a distance of the computing device from the object. 
     
     
       17. The non-transitory computer-readable storage medium of  claim 16 , wherein the location of the computing device corresponds to at least one of a GPS location, a street address, or a business establishment associated with a physical location of the computing device. 
     
     
       18. The non-transitory computer-readable storage medium of  claim 16 , wherein the instructions further cause the computing system to:
 determine a scale of the object based at least on the distance of the computing device from the object. 
 
     
     
       19. The non-transitory computer-readable storage medium of  claim 16 , wherein determining the first viewing angle of the object comprises:
 determining an orientation of a product proximate the location of the computing device; and 
 determining a viewing angle that best captures the product in the determined orientation. 
 
     
     
       20. The non-transitory computer-readable storage medium of  claim 14 , wherein the instructions further cause the computing system to:
 provide an option to purchase the item.

Cited by (0)

No later patents cite this yet.

References (0)

No backward citations on record.